Related papers: An Offline Adaptation Framework for Constrained Mu…
Consider the following instance of the Offline Meta Reinforcement Learning (OMRL) problem: given the complete training logs of $N$ conventional RL agents, trained on $N$ different tasks, design a meta-agent that can quickly maximize reward…
This study focuses on the topic of offline preference-based reinforcement learning (PbRL), a variant of conventional reinforcement learning that dispenses with the need for online interaction or specification of reward functions. Instead,…
Offline preference-based reinforcement learning (PbRL) provides an effective way to overcome the challenges of designing reward and the high costs of online interaction. However, since labeling preference needs real-time human feedback,…
Reinforcement learning (RL) has significantly advanced the control of physics-based and robotic characters that track kinematic reference motion. However, methods typically rely on a weighted sum of conflicting reward functions, requiring…
Improving the multi-step reasoning ability of large language models (LLMs) with offline reinforcement learning (RL) is essential for quickly adapting them to complex tasks. While Direct Preference Optimization (DPO) has shown promise in…
Offline Reinforcement learning (RL) has shown potent in many safe-critical tasks in robotics where exploration is risky and expensive. However, it still struggles to acquire skills in temporally extended tasks. In this paper, we study the…
In offline reinforcement learning (RL), the goal is to learn a highly rewarding policy based solely on a dataset of historical interactions with the environment. The ability to train RL policies offline can greatly expand the applicability…
In reinforcement learning (RL), there are two major settings for interacting with the environment: online and offline. Online methods explore the environment at significant time cost, and offline methods efficiently obtain reward signals by…
Offline reinforcement learning enables learning from a fixed dataset, without further interactions with the environment. The lack of environmental interactions makes the policy training vulnerable to state-action pairs far from the training…
In standard reinforcement learning (RL), a learning agent seeks to optimize the overall reward. However, many key aspects of a desired behavior are more naturally expressed as constraints. For instance, the designer may want to limit the…
While reinforcement learning (RL) methods that learn an internal model of the environment have the potential to be more sample efficient than their model-free counterparts, learning to model raw observations from high dimensional sensors…
Reinforcement learning (RL) commonly relies on scalar rewards with limited ability to express temporal, conditional, or safety-critical goals, and can lead to reward hacking. Temporal logic expressible via the more general class of…
Reinforcement learning (RL) in robotics faces significant hurdles regarding sample efficiency and generalization across varying goals. While Offline RL mitigates the need for costly online interactions, its integration with goal-conditioned…
Online matching problems arise in many complex systems, from cloud services and online marketplaces to organ exchange networks, where timely, principled decisions are critical for maintaining high system performance. Traditional heuristics…
Offline reinforcement learning algorithms still lack trust in practice due to the risk that the learned policy performs worse than the original policy that generated the dataset or behaves in an unexpected way that is unfamiliar to the…
Offline Reinforcement Learning (RL) aims to extract near-optimal policies from imperfect offline data without additional environment interactions. Extracting policies from diverse offline datasets has the potential to expand the range of…
Multi-fidelity Reinforcement Learning (RL) frameworks efficiently utilize computational resources by integrating analysis models of varying accuracy and costs. The prevailing methodologies, characterized by transfer learning, human-inspired…
There is increasing interest in data-driven approaches for recommending optimal treatment strategies in many chronic disease management and critical care applications. Reinforcement learning methods are well-suited to this sequential…
Sample-efficiency guarantees for offline reinforcement learning (RL) often rely on strong assumptions on both the function classes (e.g., Bellman-completeness) and the data coverage (e.g., all-policy concentrability). Despite the recent…
In this paper, we argue that the paradigm commonly adopted for offline evaluation of sequential recommender systems is unsuitable for evaluating reinforcement learning-based recommenders. We find that most of the existing offline evaluation…